ClawHub

Scale Frameworks

Security checks across malware telemetry and agentic risk

Overview

This is a text-only planning skill that stores disclosed local scaling notes and does not show hidden execution, exfiltration, or destructive behavior.

Reasonable to install if you want a scaling-planning framework. Review anything saved under ~/scale/ periodically, and avoid putting secrets, credentials, customer identifiers, payment data, or highly sensitive business details in the memory files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The activation criteria are overly broad and include common topics like growth, bottlenecks, and team capacity, which can cause the skill to activate in conversations where the user did not clearly request it. That increases the chance of unsolicited persistence and behavior changes, especially because the skill later instructs writing preferences to a file in the user's home directory.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs storing activation preferences in ~/scale/memory.md without any explicit user-facing notice or consent mechanism. Persistent writes to the user's home directory can retain context across sessions in a way the user may not expect, creating privacy and transparency risks even if the data is limited to preferences.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The section describing internal persistence normalizes retaining reusable user context but still does not require clear notice, consent, or reviewability. Even though it says not to store secrets or unnecessary personal data, the lack of transparent controls makes silent accumulation of behavioral preferences and operational context more dangerous.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal